Borrowing it
Nothing to install: this file belongs to wuyutanhongyuxin-cell/SJTU_CLI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wuyutanhongyuxin-cell/SJTU_CLI/main/AGENTS.mdgit clone --depth 1 https://github.com/wuyutanhongyuxin-cell/SJTU_CLIWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/wuyutanhongyuxin-cell/sjtu_cli/agents-md)<a href="https://agentmods.dev/instructions/wuyutanhongyuxin-cell/sjtu_cli/agents-md"><img src="https://agentmods.dev/badge/instructions/wuyutanhongyuxin-cell/sjtu_cli/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/wuyutanhongyuxin-cell/sjtu_cli/agents-md"><img src="https://agentmods.dev/badge/instructions/wuyutanhongyuxin-cell/sjtu_cli/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01746 | $0.01746 |
| Opus 5 | $0.00873 | $0.00873 |
| Sonnet 5 | $0.00349 | $0.00349 |
| Haiku 4.5 | $0.00175 | $0.00175 |
Grade A, and why
SJTU_CLI AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codex / 其它 AI agent 自动加载入口。 与
CLAUDE.md（Claude Code 用）并列，内容互补不冲突：本文件只写 codex 接力专属的"红线 + 当前状态 + 任务索引"。 codex 启动后必须先读完本文件 +docs/codex-handoff/SAFETY-REDLINES.md，再读CLAUDE.md补充项目宪法。
SJTU-CLI · AGENTS.md（codex 接力交接）
1. 你是谁 / 在干什么
你是 codex（OpenAI 系），接手 Claude Code 推进到一半的 SJTU-CLI 项目。 接手原因：Claude 用户额度耗尽，需要 codex 把 T5 Plan 收尾（剩 T7 验证 commit / T8 文档 / T9 用户亲跑）。
项目宪法 = CLAUDE.md（适用于所有 AI agent，不只是 Claude）。本文件覆写或扩充其中针对 codex 的部分。
2. 项目当前快照（HEAD = 980859f）
- 分支：
main - 已完成：S0..S3f / Canvas Video V5.F；T5 Plan T1..T6 已 commit
- 工作区（未 commit）：
src/cli/jwc/calendar_cli.rs（新建，27 行）— T7 文件src/cli/jwc/mod.rs（修改，200 行 整 ← 卡硬上限，不能再加内容）
- 下一步：T7 验证 + commit → T8 文档收尾 → T9 用户亲跑 4 端真机 smoke
- 详细任务索引见
docs/codex-handoff/README.md
3. 不可越界的硬红线（违反 = 立即停手）
完整版：
docs/codex-handoff/SAFETY-REDLINES.md。此处只列触发即终止的 5 条。
- i.sjtu / 交我办 = 只读访客。绝对不点"提交 / 确认 / 保存 / 绑定 / 修改 / 删除 / 退订 / 申请 / 撤回"任一按钮；绝对不触动个人信息（信息维护）与选课菜单。即使用户 session 在握，也按"只读"操作。
- 不引入新依赖。
Cargo.toml改动 = 主对话先批准。clippy / fmt 不算"新依赖"。 - 不
git push/ 不git push --force/ 不动 main 分支历史。只 commit 到本地，让用户自己 push。 - 不动既有命令的 envelope（grades / schedule / gpa / exams / today / week / next / login 等）。只能新增字段，不能改既有字段名 / 类型 / 含义。
- 不动这些目录 / 文件（已有真实数据或敏感配置）：
~/.sjtu-cli/（用户 session）tests/fixtures/jwc/academic_calendar_*.json（已落盘 fixture，T6 已用）- 任何含
session.json/cookies.json/ 真实学号姓名的文件
4. 接力 driven 工作流（codex 自走）
详见 docs/codex-handoff/DRIVEN-WORKFLOW.md。核心 4 条：
- fresh subagent per task（如 codex 支持 subagent / 子会话）—— 不让一个 agent 同时背 3 个 task 上下文，污染极重。
- 两阶段 review：实装 agent → spec compliance 检查 agent → code quality 检查 agent → 通过才 commit。
- trust but verify：subagent 报告"DONE"必须自己跑
cargo check+cargo clippy --all-targets -- -D warnings+cargo fmt --all -- --check+wc -l三件套 亲自核验，不信 agent 的口述。 - 遇阻立即停 + 报告主对话，不要自作主张大改。
docs/codex-handoff/README.md给出每个 task 的"停手判断条件"。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 103 lines · 1,746 tokens per session scan A a780306a905f
SJTU_CLI AGENTS.md is an instructions file published in the GitHub repository wuyutanhongyuxin-cell/SJTU_CLI (49 stars, last pushed 3mo ago), licensed MIT. It adds 1,746 tokens to every session, about $0.0087 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.